Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

SQSHRN (4S)

Test 1: uops

Code:

  sqshrn v0.4h, v0.4s, #3
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303723126125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
1004303722038425472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372306125472510001000100039816013018303730372414328951000100010003037303711100110000073216222629100030383038303830383038
100430372206125472510001000100039816003018303730372414328951000100010003037303711100110000073216222629100030383038303830383038

Test 2: Latency 1->2

Code:

  sqshrn v0.4h, v0.4s, #3
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)03070a1e3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8a9c5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
10204300372251100275295472510100100100001001000050042771600300183003730037282716287401010020010008200100083003730037111020110099100100100001004001117171161129648100001003003830038300383003830038
1020430037225110082295472510100100100001001000050042771601300183003730037282717287411010020010008200100083003730037111020110099100100100001000001117181161129647100001003003830038300383003830038
10204300372241100103295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
10204300372250000529295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383008530038
10204300372250000166295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
1020430037225000061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
1020430037224000061295472510100100100001001000050042771600300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038
1020430037225009061295472510100100100001001000050042771601300183003730037282643287451010020010000200100003003730037111020110099100100100001000000007102162229633100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)0308090b18191e1f3a3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa0a1a6a7a8a9accfd5d6ddinst fetch restart (de)e0? int output thing (e9)? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722500000000545295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006403162229629010000103003830038300383003830038
100243003722500000000166295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722400000000486295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000768295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000001006402162229629010000103003830038300383003830038
10024300372240000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000200006402162229629010000103003830038300383003830038
10024300372250000000061295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000147295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000036402162229629010000103003830038300383003830038
100243003722500000000166295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000126295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003711100211091010100001000000006402162229629010000103003830038300383003830038
100243003722500000000103295472510010101000010100005042771600300183003730037282863287671001020100002010000300373003721100211091010100001000000006402162229629010000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  sqshrn v0.4h, v8.4s, #3
  sqshrn v1.4h, v8.4s, #3
  sqshrn v2.4h, v8.4s, #3
  sqshrn v3.4h, v8.4s, #3
  sqshrn v4.4h, v8.4s, #3
  sqshrn v5.4h, v8.4s, #3
  sqshrn v6.4h, v8.4s, #3
  sqshrn v7.4h, v8.4s, #3
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 0.2506

retire (01)cycle (02)031e3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa6a8acc5branch mispredict (cb)cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80204200601501230258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391502130258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391502130258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391501272258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
8020420039150330258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200941501230258010810080116100800205006401320200200200392003999776999080228200800322008003220039201012180201100991001008000010000011151180160020036800001002004020040200402004020040
80204200391503930258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915045630258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040
802042003915032430258010810080008100800205006401320200200200392003999776999080120200800322008003220039200391180201100991001008000010000311151180160020036800001002004020040200402004020040
802042003915050430258010810080008100800205006401321200200200392003999776999080120200800322008003220039200391180201100991001008000010000011151180160020036800001002004020040200402004020040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 0.2505

retire (01)cycle (02)031e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696b6d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fcfd0d5d6ddinst fetch restart (de)e0eb? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
8002420039150004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000105020212216212120036080000102004020040200402004020040
8002420039149004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000105020182216212120036080000102004020091200402004020040
8002420039150088402580010108000010800005064000012002002003920039999631001980010208000020800002003920039118002110910108000010502018191692120036080000102004020040200402004020040
800242003915000402580010108000010800005064000002002002003920039999631001980010208000020800002003920039118002110910108000010502015211692120036080000102004020040200402004020040
80024200391500040258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001050201591621920036080000102004020040200402004020040
8002420039150004025800101080000108000050640000020020020039200399996310019800102080000208000020039200391180021109101080000105020182116212120036080000102004020040200402004020040
8002420039150150294258001010800001080000506400000200200200392003999963100198001020800002080000200392003911800211091010800001050201821162121200362080000102004020040200402004020040
800242003915000402580010108000010800005064000012002002003920039999631001980010208000020800002003920039118002110910108000010502018211621920036080000102004020040200402004020040
8002420039150004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000105020182116212120036080000102004020040200402004020040
8002420039150004025800101080000108000050640000120020020039200399996310019800102080000208000020039200391180021109101080000105020182116211020036080000102004020040200402004020040